Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    alphabet idioms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rashed
    0.50
    ாலை
    0.50
     કરો
    0.48
    Elapsed
    0.47
    सभी
    0.47
     wyposaż
    0.46
     करो
    0.45
    ผ่าน
    0.45
     گاڑی
    0.44
    ຕ້ອງ
    0.44
    POSITIVE LOGITS
     optimality
    0.47
     cosmology
    0.43
     репре
    0.41
     こと
    0.40
     welt
    0.40
     existential
    0.40
    ivism
    0.38
    เร
    0.38
     представи
    0.37
    oplevel
    0.37
    Act Density 0.001%

    No Known Activations